doc-prd-fixer

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Phase 6.0.1 (Hash Validation Fixes) involves the execution of the 'sha256sum' system utility via a shell pipe to calculate and verify file hashes for drift detection.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it ingests and processes untrusted data from external PRD, BRD, and Audit/Review reports to perform automated document modifications. * Ingestion points: Reads content from PRD, BRD, and Audit/Review report files provided in the project directory. * Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the processed documentation. * Capability inventory: The skill performs file system operations including directory creation (os.makedirs), file moving (shutil.move), and file writing (Path.write_text), alongside shell command execution. * Sanitization: No sanitization, escaping, or validation of the ingested document content is performed before processing or writing back to the file system.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 11:59 AM
Security Audit — agent-trust-hub — doc-prd-fixer